Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    occurrences of the pronoun "I" and related references in discourse

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ovich
    -0.15
    arshal
    -0.14
    ertain
    -0.14
    cheon
    -0.14
     Certain
    -0.14
    oro
    -0.13
    inar
    -0.13
    Ñģл
    -0.13
     landed
    -0.13
    til
    -0.13
    POSITIVE LOGITS
    NullException
    0.17
    /us
    0.17
    ÅĻes
    0.15
    ãĥ³ãĥķ
    0.15
    rlen
    0.14
    ccak
    0.14
     halde
    0.14
    åĢij
    0.14
    elen
    0.14
    ãģªãĤĵãģł
    0.13
    Act Density 0.114%

    No Known Activations